Virtual power plant electric power bidding strategy determination method and device, equipment and medium

Abstract

The invention provides a virtual power plant electric power bidding strategy determination method and device, equipment and a medium, and the method comprises the steps: constructing an input vector based on the predicted clearing electricity price of a power grid node of a virtual power plant; the input vector is input into a bidding strategy model, a bidding strategy of the virtual power plant is output, and the bidding strategy comprises the electricity selling price, the electricity selling capacity, the electricity purchasing price and the electricity purchasing capacity; the objective function of the bidding strategy model is constructed by taking the maximum total profit of the virtual power plant as an objective; the total profit is determined based on the electricity selling income, the electricity purchasing expenditure and the electricity generation cost of the virtual power plant. According to the method, the seller characteristics of the virtual power plant after the distributed resources are aggregated are utilized, the clearing electricity price of each member node is predicted at the same time, and then the bidding strategies including the electricity selling price, the electricity selling capacity, the electricity purchasing price and the electricity purchasing capacity are predicted by taking the maximum total profit as the target, so that the virtual power plant transacts in the electricity market with double identities, and the transaction efficiency is improved. The utilization rate of aggregated electric power resources is improved to the maximum extent, it is guaranteed that generated electric power can be supplied to the market, and resource waste is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of power management, and in particular to a method, device, equipment and medium for determining a power bidding strategy for a virtual power plant. Background Art

[0002] A virtual power plant is a virtual power supply network formed by aggregating multiple distributed energy resources (DER).

[0003] When existing virtual power plants participate in electricity market transactions, the bidding strategies they provide generally only include electricity sales prices and electricity sales capacity.

[0004] However, since the bidding strategy provided by the virtual power plant only includes the electricity sales price and electricity sales capacity, once the bid fails, the electricity generated by the multiple DERs aggregated by the virtual power plant during the corresponding trading period will not be able to be supplied to the market. In addition to being unable to obtain electricity sales revenue, it will also lead to a decrease in the utilization rate of power generation equipment, resulting in a waste of resources. Summary of the invention

[0005] The present invention provides a method, device, equipment and medium for determining a power bidding strategy for a virtual power plant, so as to solve the defect that the bidding strategy in the prior art only includes the power selling price and the power selling capacity, and to take into account the power revenue and the power generation power to the greatest extent when determining the power bidding strategy.

[0006] The present invention provides a method for determining a virtual power plant power bidding strategy, comprising: Construct an input vector based on the predicted clearing electricity prices of the grid nodes of the virtual power plant; Inputting the input vector into a bidding strategy model, and outputting a bidding strategy of the virtual power plant, wherein the bidding strategy includes a power selling price, a power selling capacity, a power purchasing price, and a power purchasing capacity; The objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power sales revenue, power purchase expenditure and power generation cost of the virtual power plant.

[0007] According to a method for determining a virtual power plant power bidding strategy provided by the present invention, the predicted clearing electricity price includes a day-ahead clearing electricity price and a real-time clearing electricity price; The predicted clearing electricity price of the grid node based on the virtual power plant is used to construct an input vector, including: The input vector is constructed using the day-ahead clearing electricity price, the real-time clearing electricity price, the predicted power generation and the predicted power consumption of the power grid node.

[0008] According to a method for determining a virtual power plant power bidding strategy provided by the present invention, the power sales revenue is determined based on the day-ahead power sales revenue and the real-time power sales revenue; the power purchase expenditure is determined based on the day-ahead power purchase expenditure and the real-time power purchase expenditure; The day-ahead electricity sales revenue is determined based on the day-ahead clearing electricity prices and predicted power generation of all winning generation nodes; the winning generation node is a generation node whose day-ahead clearing price is greater than the electricity sales price; The real-time electricity sales revenue is determined based on the real-time clearing electricity prices and predicted power generation of all non-bid-winning power generation nodes; the non-bid-winning power generation nodes are power generation nodes whose day-ahead clearing prices are lower than the electricity sales price; The day-ahead electricity purchase expenditure is determined based on the day-ahead clearing electricity prices and predicted electricity consumption of all winning electricity consumption nodes; the winning electricity consumption node is an electricity consumption node whose day-ahead clearing electricity price is less than the electricity purchase price; The real-time electricity purchase expenditure is determined based on the real-time clearing electricity price and predicted electricity consumption of all non-bid electricity consumption nodes, and the non-bid electricity consumption nodes are electricity consumption nodes whose day-ahead clearing electricity price is greater than the electricity purchase price.

[0009] According to a method for determining a virtual power plant power bidding strategy provided by the present invention, the power generation cost is determined based on the initial investment cost and operation and maintenance cost of all power generation equipment at the power generation node; The power generation equipment includes at least one of a photovoltaic power generation group, a wind power generation group, a pumped storage power station and an energy storage battery.

[0010] According to a method for determining a virtual power plant power bidding strategy provided by the present invention, before constructing an input vector based on the predicted clearing power price of a power grid node of the virtual power plant, the method further includes: Receive valid basic information of the power generation equipment sent by the front end; the valid basic information is basic information that satisfies validity verification; the basic information is input to the front end by the user through the user interface; The valid basic information that satisfies the integrity check is stored in the database.

[0011] According to a method for determining a bidding strategy for a virtual power plant provided by the present invention, after inputting the input vector into a bidding strategy model and outputting the bidding strategy for the virtual power plant, the method further comprises: Determine the magnitude relationship between the electricity selling price and the minimum electricity selling price; If the electricity selling price is lower than the minimum electricity selling price, the minimum electricity selling price is used as the new electricity selling price; the minimum electricity selling price is determined based on the minimum power generation cost of all power generation equipment in the virtual power plant; Determine the magnitude relationship between the electricity purchase price and the maximum electricity purchase price; If the electricity purchase price is higher than the maximum electricity purchase price, the maximum electricity purchase price is used as the new electricity purchase price; the maximum electricity purchase price is determined based on the electricity user's historical electricity purchase data.

[0012] The present invention also provides a device for determining a virtual power plant power bidding strategy, comprising the following modules: A vector construction module, used to construct an input vector based on the predicted clearing electricity prices of the grid nodes of the virtual power plant; A strategy acquisition module, used to input the input vector into a bidding strategy model, and output a bidding strategy of the virtual power plant, wherein the bidding strategy includes a power selling price, a power selling capacity, a power purchasing price, and a power purchasing capacity; The objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power sales revenue, power purchase expenditure and power generation cost of the virtual power plant.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements any of the above-described methods for determining a virtual power plant electricity bidding strategy.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the methods for determining a virtual power plant electricity bidding strategy as described above.

[0015] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned methods for determining a virtual power plant electricity bidding strategy.

[0016] The method, device, equipment and medium for determining the power bidding strategy of a virtual power plant provided by the present invention utilize the producer-seller characteristics of the virtual power plant after aggregating distributed resources, and simultaneously predict the clearing electricity price of each grid node, and then predict the bidding strategy including the power selling price, power selling capacity, power purchasing price and power purchasing capacity with the goal of maximizing total profit, so that the virtual power plant can trade in the power market with a dual identity, maximize the utilization rate of the aggregated power resources, ensure that the generated power can be supplied to the market, and avoid wasting resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is a flow chart of the method for determining the power bidding strategy of a virtual power plant provided by the present invention.

[0019] Figure 2 This is an example diagram of submitting basic information of power generation equipment provided by the present invention.

[0020] Figure 3 This is an example diagram of submitting basic information of load equipment provided by the present invention.

[0021] Figure 4 It is a structural schematic diagram of a device for determining a virtual power plant power bidding strategy provided by the present invention.

[0022] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Combine the following Figure 1-Figure 5 The present invention describes a method, device, equipment and medium for determining a virtual power plant power bidding strategy.

[0025] A virtual power plant is a power coordination management system that uses advanced information and communication technologies and software systems to achieve aggregation and coordinated optimization of DERs, so that they can participate in the electricity market and power grid operations as a special power plant. After integrating DERs through technical means, the virtual power plant forms a virtual power supply network. The most attractive function of a virtual power plant is that it can aggregate DERs to participate in the operation of the electricity market and ancillary service market, and provide management and ancillary services for the distribution network and transmission network.

[0026] After multiple DERs are aggregated into a virtual power plant, the virtual power plant trades electricity with the power market at a unified bidding price and bidding capacity on behalf of all DERs. If all the electricity generated by DERs can be sold, it not only maximizes the revenue from electricity sales, but also means that the power generation equipment aggregated by the virtual power plant can generate electricity at the highest power, which can improve the utilization rate of the power generation equipment and maximize the power generation of the power generation equipment aggregated by the virtual power plant.

[0027] Figure 1 : is a flow chart of a method for determining a bidding strategy for a virtual power plant provided by the present invention, such as Figure 1As shown, the method for determining the virtual power plant electricity bidding strategy includes but is not limited to the following steps 101 and 102.

[0028] Step 101: construct an input vector based on the predicted clearing electricity prices of the grid nodes of the virtual power plant.

[0029] The predicted clearing electricity price is the expected transaction price of each grid node aggregated by the virtual power plant in the corresponding trading period obtained through prediction.

[0030] Although a virtual power plant is not a physical power plant, it aggregates several grid nodes, each of which is connected to several DERs. DERs can include photovoltaic generators, wind turbines, small pumped storage power stations, energy storage batteries and other power generation equipment, which need to sell the electricity they produce during trading hours; they can also include energy storage batteries, small electricity users and other load equipment, which need to purchase the electricity they need to operate during trading hours.

[0031] It can be seen that equipment like energy storage batteries can be used as both power generation equipment and load equipment.

[0032] Specifically, the predicted clearing electricity prices of each grid node aggregated by the virtual power plant in a certain trading period are obtained, and an input vector is constructed according to the predicted clearing electricity prices of each grid node.

[0033] It is understandable that a trading session can be either a trading day or a period of time within a trading day.

[0034] For example, a trading day can be divided into T equal time periods. T=24 The trading period is one of the 24 time periods, and the virtual power plant reports its bidding strategy to the trading market according to the 24 trading periods.

[0035] Step 102: input the input vector into a bidding strategy model, and output the bidding strategy of the virtual power plant; the bidding strategy includes electricity selling price, electricity selling capacity, electricity purchasing price and electricity purchasing capacity.

[0036] The objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power sales revenue, power purchase expenditure and power generation cost of the virtual power plant.

[0037] The bidding strategy includes the electricity sales price and electricity purchase price of the virtual power plant in the corresponding trading period, as well as the electricity sales capacity and electricity purchase capacity of the virtual power plant in the corresponding trading period.

[0038] Electricity sales revenue refers to the fees earned by all the generating units aggregated by the virtual power plant from selling electricity with sales capacity in the electricity trading market according to the electricity sales price output by the bidding strategy model; electricity purchase expenditure refers to the fees paid by all the loads aggregated by the virtual power plant from buying electricity with purchase capacity in the electricity trading market according to the electricity purchase price output by the bidding strategy model.

[0039] Specifically, the bidding strategy model is pre-built and trained. When building the bidding strategy model, the total profit is determined based on the electricity sales revenue, electricity purchase expenditure and power generation cost of all grid nodes aggregated by the virtual power plant, and the total profit of all grid nodes aggregated by the virtual power plant is maximized, thereby determining the objective function of the bidding strategy model.

[0040] When determining the bidding strategy, the predicted clearing electricity price of each grid node of the virtual power plant in a certain trading period is obtained based on the prediction method, and the input vector is constructed based on the predicted clearing electricity price of each grid node. The input vector is input into the trained bidding strategy model, and the bidding strategy including the power selling price, power selling capacity, power purchasing price and power purchasing capacity is output. The virtual power plant bids to the power market in the corresponding trading period based on the obtained power selling price, power selling capacity, power purchasing price and power purchasing capacity.

[0041] It should be noted that the bidding strategy model can be built based on any one of the machine learning models such as the Long Short-Term Memory (LSTM) model, the Back Propagation (BP) model, the Random Forest (RF) model, the Multi-layer Perceptron (MLP) model and the Prophet model, which will not be elaborated in the present invention.

[0042] It is understandable that virtual power plants can only participate in market transactions in a dual capacity when the aggregated capacity of virtual power plants is not sufficient to affect the market clearing price.

[0043] The method for determining the power bidding strategy of a virtual power plant provided by the present invention utilizes the producer-seller characteristics of the virtual power plant after aggregating distributed resources, and simultaneously predicts the clearing electricity price of each member node, and then predicts the bidding strategy including the power selling price, power selling capacity, power purchasing price and power purchasing capacity with the goal of maximizing the total profit, so that the virtual power plant can trade in the power market with a dual identity according to the bidding strategy, maximize the utilization rate of the aggregated power resources, ensure that the generated power can be supplied to the market, and avoid wasting resources.

[0044] Based on the above embodiment, as an optional embodiment, the predicted clearing electricity price includes a day-ahead clearing electricity price and a real-time clearing electricity price; The predicted clearing electricity price of the grid node based on the virtual power plant is used to construct an input vector, including: The input vector is constructed using the day-ahead clearing electricity price, the real-time clearing electricity price, the predicted power generation and the predicted power consumption of the power grid node.

[0045] The day-ahead market is a form of electricity market trading that allows participants to buy and sell electricity based on the forecast supply and demand conditions one day before the actual electricity transaction. By participating in the day-ahead market, electricity market participants can fix part of their power generation and consumption plans on the trading day in advance.

[0046] The day-ahead clearing electricity price is the expected transaction price of the grid node in the corresponding trading period of the day-ahead market, obtained through forecasting.

[0047] Optionally, the day-ahead clearing electricity price is output by the day-ahead clearing electricity price prediction model after historical day-ahead clearing electricity prices, historical energy prices and historical weather data for a preset time period are input into the day-ahead clearing electricity price prediction model.

[0048] The real-time clearing electricity price is the expected transaction price of the grid node in the corresponding trading period of the real-time market obtained through prediction.

[0049] Optionally, the real-time clearing electricity price is output by the real-time clearing electricity price prediction model after inputting historical real-time clearing electricity prices, historical energy prices and historical weather data for a preset time period into the real-time clearing electricity price prediction model.

[0050] The predicted power generation is the power generation of the grid node in the corresponding trading period obtained by prediction.

[0051] Optionally, the predicted power generation is output by inputting historical power generation in a preset time period, historical weather data and power generation equipment performance data corresponding to the power generation node into a power generation prediction model.

[0052] The predicted electricity consumption is the electricity consumption of the power grid node during the corresponding trading period obtained through prediction.

[0053] Optionally, the predicted electricity consumption is obtained by inputting historical electricity consumption, historical weather data and high electricity consumption date data for a preset time period into an electricity consumption prediction model, and outputting the electricity consumption prediction model.

[0054] It should be noted that each prediction model in the day-ahead clearing electricity price prediction model, the real-time clearing electricity price prediction model, the power generation prediction model and the electricity consumption prediction model can be built based on any machine learning model such as the LSTM model, the BP model, the RF model, the MLP model and the Prophet model.

[0055] As an optional embodiment, the day-ahead clearing electricity price prediction model based on the LSTM model is trained according to the following steps: The historical day-ahead clearing electricity prices, historical energy prices and historical weather data of each power grid node in the historical time period are collected and converted into time series sample vectors suitable for the LSTM model. The historical day-ahead clearing electricity prices of the corresponding trading periods are used as the label data corresponding to the time series sample vectors.

[0056] In each training iteration, the time series sample vector is input into the day-ahead clearing electricity price prediction model built based on the LSTM model. The error (such as mean square error, mean absolute error, etc.) between the output data of the day-ahead clearing electricity price prediction model and the label data is calculated according to the loss function. The back propagation algorithm is used to adjust the weight and bias of the day-ahead clearing electricity price prediction model according to the error, and gradually optimize the prediction performance of the day-ahead clearing electricity price prediction model until the value of the loss function meets the accuracy condition and the day-ahead clearing electricity price prediction model is trained.

[0057] It should be noted that the training methods of the real-time clearing electricity price prediction model, the power generation prediction model and the electricity consumption prediction model can refer to the training steps of the aforementioned day-ahead clearing electricity price prediction model and be combined with the specific model structure, which will not be elaborated in the present invention.

[0058] Specifically, based on the prediction method, the historical day-ahead clearing electricity price, historical real-time clearing electricity price, historical energy prices, historical weather data, historical power generation, historical power consumption, power generation equipment performance data corresponding to the power generation node and high power consumption date data within a preset time period are input into the corresponding prediction model to obtain the day-ahead clearing electricity price, real-time clearing electricity price, predicted power generation and predicted power consumption of the power grid node in the corresponding trading period.

[0059] An input vector is constructed according to the day-ahead clearing electricity price, real-time clearing electricity price, predicted power generation and predicted electricity consumption of each grid node, so as to input the input vector into the bidding strategy model and output the bidding strategy of the virtual power plant.

[0060] The method for determining the power bidding strategy of a virtual power plant provided by the present invention simultaneously predicts the clearing electricity prices of the power grid nodes of the virtual power plant in the day-ahead market and the real-time market, and is based on the virtual power plant's participation in the day-ahead market to fix part of the power generation and power consumption plans on the trading day. As a result, on the trading day, the virtual power plant can, based on part of the power generation and power consumption plans fixed in the day-ahead market, make real-time and flexible adjustments to the power generation and power consumption plans of the power grid nodes, so as to improve the overall utilization rate of electric energy and avoid waste of resources.

[0061] Based on the above embodiment, as an optional embodiment, the electricity sales revenue is determined based on the day-ahead electricity sales revenue and the real-time electricity sales revenue; the electricity purchase expenditure is determined based on the day-ahead electricity purchase expenditure and the real-time electricity purchase expenditure; The day-ahead electricity sales revenue is determined based on the day-ahead clearing electricity prices and predicted power generation of all winning generation nodes; the winning generation node is a generation node whose day-ahead clearing price is greater than the electricity sales price; The real-time electricity sales revenue is determined based on the real-time clearing electricity prices and predicted power generation of all non-bid-winning power generation nodes; the non-bid-winning power generation nodes are power generation nodes whose day-ahead clearing prices are lower than the electricity sales price; The day-ahead electricity purchase expenditure is determined based on the day-ahead clearing electricity prices and predicted electricity consumption of all winning electricity consumption nodes; the winning electricity consumption node is an electricity consumption node whose day-ahead clearing electricity price is less than the electricity purchase price; The real-time electricity purchase expenditure is determined based on the real-time clearing electricity price and predicted electricity consumption of all non-bid electricity consumption nodes, and the non-bid electricity consumption nodes are electricity consumption nodes whose day-ahead clearing electricity price is greater than the electricity purchase price.

[0062] The power generation node is the grid node that can generate electricity in the virtual power plant; the power consumption node is the grid node that serves as a load in the virtual power plant.

[0063] The day-ahead electricity sales revenue refers to the fees obtained by the power generation nodes aggregated by the virtual power plant and winning the bid in the day-ahead market by selling electricity corresponding to the predicted power generation at the electricity sales price output by the bidding strategy model.

[0064] Real-time electricity sales revenue refers to the fees obtained by the power generation nodes aggregated by the virtual power plant and winning the bid in the real-time market by selling electricity corresponding to the predicted power generation at the electricity sales price output by the bidding strategy model.

[0065] The day-ahead electricity purchase expenditure refers to the cost incurred by the electricity consumption nodes aggregated by the virtual power plant and winning the bid in the day-ahead market when purchasing electricity corresponding to the predicted electricity consumption according to the electricity purchase price output by the bidding strategy model.

[0066] Real-time electricity purchase expenditure refers to the cost incurred by the electricity consumption nodes aggregated by the virtual power plant in the real-time market when purchasing electricity corresponding to the predicted electricity consumption according to the electricity purchase price output by the bidding strategy model.

[0067] Optionally, the day-ahead electricity sales revenue of the virtual power plant is determined according to the following expression (1):

[0068] in, is the day-ahead electricity sales revenue of the virtual power plant; is the number of trading sessions in a trading day; is the number of grid nodes aggregated by the virtual power plant; represents the day-ahead market; is the indicator function; is the electricity selling price in the bidding strategy; For the Grid nodes during trading hours The day-ahead clearing electricity price; hour, Take 1, otherwise take 0; For the Grid nodes during trading hours The predicted power generation; For the The collection of power generation equipment connected to each grid node; For the The total power generation cost of the power generation equipment connected to each grid node; For the time interval.

[0069] Optionally, the power generation winning rate of the grid node in the virtual power plant is determined according to the following expression (2):

[0070] in, is the power generation winning rate, is the number of trading sessions in a trading day; The number of grid nodes aggregated for the virtual power plant; is the indicator function; is the electricity selling price in the bidding strategy; For the Grid nodes during trading hours The day-ahead clearing electricity price; hour, Take 1, otherwise take 0.

[0071] when This indicates that in the day-ahead market, the virtual power plant The power generation equipment connected to the grid nodes during the trading period The power grid pays the power purchase fee to the virtual power plant according to the clearing result, and the virtual power plant then sells the power to the third party according to the power selling price in the bidding strategy. The power generation equipment connected to each grid node pays the electricity purchase fee. The power generation equipment connected to each grid node will generate power during the trading period according to the predicted power generation on the trading day. Power generation.

[0072] when This indicates that in the day-ahead market, the virtual power plant The power generation equipment connected to the grid nodes during the trading period Average flow, The power generation equipment connected to each grid node needs to sell electricity to the grid according to the real-time electricity price or the on-grid electricity price on the trading day. At this time, the real-time electricity sales income of the virtual power plant can be determined by referring to expression (1).

[0073] Optionally, the day-ahead electricity purchase expenditure of the virtual power plant is determined according to the following expression (3):

[0074] in, The day-ahead electricity purchase expenditure of the virtual power plant; is the number of trading sessions in a trading day; is the number of grid nodes aggregated by the virtual power plant; represents the day-ahead market; is the indicator function; is the electricity purchase price in the bidding strategy; For the Grid nodes during trading hours The day-ahead clearing electricity price; hour, Take 1, otherwise take 0; For the Grid nodes during trading hours Forecasted electricity consumption; For the The set of load members connected to each grid node; For the time interval.

[0075] Optionally, the load winning rate of the grid node in the virtual power plant is determined according to the following expression (4):

[0076] in, is the load winning rate, is the number of trading sessions in a trading day; The number of grid nodes aggregated for the virtual power plant; is the indicator function; is the electricity purchase price in the bidding strategy; For the Grid nodes during trading hours The day-ahead clearing electricity price; hour, Take 1, otherwise take 0.

[0077] when This indicates that in the day-ahead market, the virtual power plant The load members connected to the grid nodes are in the trading period All won the bid, The load members connected to each grid node pay the electricity purchase fee to the virtual power plant according to the electricity purchase price in the bidding strategy, and the virtual power plant then purchases electricity from the grid according to the day-ahead clearing electricity price of each node, and the grid delivers the corresponding amount of electricity within the trading day.

[0078] when This indicates that in the day-ahead market, the virtual power plant The load members connected to the grid nodes are in the trading period Equalizing current bid, virtual power plant The load members connected to each grid node need to pay the electricity fee according to the real-time electricity price on the trading day. At this time, the real-time electricity purchase expenditure of the virtual power plant can be determined by referring to expression (3).

[0079] When a virtual power plant participates in the day-ahead market bidding as an electricity resource, it can purchase electricity on the trading day in advance at a price that is lower than the psychologically expected upper limit electricity price of the load members connected to the grid nodes aggregated by the virtual power plant. This not only reduces the price risk it needs to bear in the real-time market on the trading day, but also effectively reminds members of the nodes that have not won the bid to avoid possible peak electricity price periods.

[0080] The present invention provides a method for determining a virtual power plant electricity bidding strategy. The virtual power plant, as an electricity resource, participates in the day-ahead market bidding and can fix part of the electricity consumption plan on the trading day. As a result, on the trading day, the virtual power plant can, based on part of the electricity consumption plan fixed in the day-ahead market, make real-time and flexible adjustments to the electricity consumption plans of the electricity consumption nodes, so as to improve the overall resource utilization and avoid waste of resources.

[0081] Based on the above embodiment, as an optional embodiment, the power generation cost is determined according to the initial investment cost and operation and maintenance cost of all power generation equipment of the power generation node; The power generation equipment includes at least one of a photovoltaic power generation group, a wind power generation group, an energy storage power station and an energy storage battery.

[0082] Optionally, the energy storage power station is a small pumped storage power station.

[0083] When constructing the objective function of the bidding strategy model with the goal of maximizing the total profit of the virtual power plant, the total profit is determined based on the power sales revenue, power purchase expenditure and power generation cost of the virtual power plant. Among them, the power generation cost is determined based on the initial investment cost and operation and maintenance cost of all power generation equipment connected to all power generation nodes aggregated by the virtual power plant.

[0084] Furthermore, the power generation equipment includes at least one of photovoltaic power generation groups, wind power generation groups, energy storage power stations and energy storage batteries. When there are multiple power generation equipment, it can be a combination of photovoltaic power generation groups, wind power generation groups, energy storage power stations and energy storage batteries.

[0085] Optionally, the power generation cost of the photovoltaic power generation group is determined according to the following expression (5):

[0086] in, is the power generation cost of the photovoltaic generator set, 10,000 yuan; is the residual value, ten thousand yuan; is the discount rate; is the operating life of the photovoltaic generator set, ; is the annual operation and maintenance cost of the photovoltaic generator set, 10,000 yuan; is the financial cost of the photovoltaic power generation unit, i.e., loan interest expenditure, 10,000 yuan; The tax for photovoltaic power generation units, including value-added tax and surcharge, is RMB 10,000; Photovoltaic generator set Total electricity generated in the year, kWh.

[0087] Optionally, the power generation cost of the wind turbine generator set is determined according to the following expression (6):

[0088] in, is the power generation cost of the wind turbine, 10,000 yuan; is the initial investment cost of the wind turbine generator set, ten thousand yuan; is the annual operation and maintenance cost of the wind turbine, 10,000 yuan; is the annual operating cost of the wind turbine, 10,000 yuan; For wind turbines Total electricity generated in the year, kWh; is the discount rate; is the operating life of the wind turbine generator set, .

[0089] Optionally, the power generation cost of the energy storage power station is determined according to the following expression (7):

[0090] in, is the power generation cost of the energy storage power station, 10,000 yuan; is the initial investment cost of the energy storage power station, 10,000 yuan; is the residual value, ten thousand yuan; is the discount rate; is the operating life of the energy storage power station, ; is the annual operation and maintenance cost of the energy storage power station, 10,000 yuan; is the financial cost of the energy storage power station, 10,000 yuan; Taxes and fees for energy storage power stations, RMB 10,000; For energy storage power station Total electricity generated in the year, kWh.

[0091] Optionally, the power generation cost of the energy storage battery is determined according to the following expression (8):

[0092] in, The power generation cost of the energy storage battery is 10,000 yuan; is the initial investment cost of the energy storage battery, 10,000 yuan; The operation and maintenance cost of the energy storage battery is RMB 10,000; is the unit capacity replacement cost, RMB / kWh; is the average annual reduction rate of energy storage costs; The year of battery replacement; is the discount rate; is the operating life of the energy storage battery, including the year after battery replacement, .

[0093] Understandably, The total power generation cost of the power generation equipment connected to the power generation node , can be determined based on the number of photovoltaic power generation units, wind power generation units, energy storage power stations, energy storage batteries and other power generation equipment in the power generation equipment, combined with the above expressions (5)(6)(7)(8).

[0094] The method for determining the power bidding strategy for a virtual power plant provided by the present invention fully considers the power generation costs of power generation equipment such as photovoltaic power generation groups, wind power generation groups, energy storage power stations and energy storage batteries, and uses the power generation costs as an influencing factor in determining the power bidding strategy. While improving the overall utilization rate of electric energy and avoiding waste of resources, it ensures that the distributed resources aggregated by the virtual power plant are not harmed.

[0095] As an optional embodiment, when constructing the objective function of the bidding strategy model with the goal of maximizing the total profit of the virtual power plant, it is also assumed that: (1) all predicted power generation of power generation equipment connected to power generation nodes that did not win the bid in the day-ahead market will be sold in the real-time market; (2) all predicted power consumption of load members connected to power consumption nodes that did not win the bid in the day-ahead market will be purchased in the real-time market.

[0096] Furthermore, the objective function of the bidding strategy model is determined based on the following expression (9):

[0097] in, ; For the Power generation nodes during trading hours The day-ahead electricity sales revenue; For the Power generation nodes during trading hours Real-time electricity sales revenue; For the All power generation equipment connected to the power generation node during the trading period The cost of electricity generation; ; For the Power consumption nodes during trading hours The day-ahead electricity purchase expenditure; For the Power consumption nodes during trading hours Real-time electricity purchase expenditure.

[0098] Furthermore, the power sales capacity of the virtual power plant in the day-ahead market output by the bidding prediction model needs to satisfy the constraint that the power sales capacity is equal to the sum of the power generation of the power generation equipment connected to each power generation node of the virtual power plant and the dischargeable capacity of the energy storage. This constraint can be determined by the following expressions (10)-(14):

[0099] in, For the All power generation equipment connected to the power generation node during the trading period The electricity sales capacity; For the During the trading period, the photovoltaic power generation groups connected to the power generation nodes The electricity sales capacity; For the The wind turbines connected to the power generation nodes are The electricity sales capacity; For the The energy storage power station connected to the power generation node is in the trading period The electricity sales capacity; For the The energy storage batteries connected to the power generation nodes are The electricity sales capacity; For the During the trading period, the photovoltaic power generation groups connected to the power generation nodes The predicted power generation; For the The wind turbines connected to the power generation nodes are The predicted power generation; For the The energy storage power station connected to the power generation node is in the trading period The predicted power generation; For the The energy storage batteries connected to the power generation nodes are The predicted power generation, The interval between trading sessions.

[0100] Furthermore, for the power purchase capacity of the virtual power plant in the day-ahead market output by the bidding prediction model, it is necessary to satisfy the constraint that the power purchase capacity is equal to the sum of the power consumption of the load equipment connected to each power consumption node of the virtual power plant and the rechargeable capacity of the energy storage. This constraint can be determined by the following expressions (15)-(17):

[0101] in, For the All load devices connected to the power consumption node during the trading period Power purchase capacity; For the During the trading period, the small power users connected to the power nodes Power purchase capacity; For the The energy storage batteries connected to the power consumption nodes during the trading period Power purchase capacity; For the During the trading period, the small power users connected to the power nodes Forecasted electricity consumption; For the The energy storage batteries connected to the power consumption nodes during the trading period Forecasted electricity consumption; The interval between trading sessions.

[0102] Furthermore, the energy storage battery needs to satisfy the constraints determined by the following expressions (18)-(20) during operation:

[0103] in, For the The energy storage batteries connected to the power generation nodes are Maximum discharge power; For the The energy storage batteries connected to the power consumption nodes during the trading period Maximum charging power; For the The energy storage batteries connected to the power generation nodes are The discharge state variable of For the The energy storage batteries connected to the power consumption nodes during the trading period The charge state variable.

[0104] Furthermore, the power sales capacity and power purchase capacity of the virtual power plant in the real-time market should satisfy the constraints determined by the following expressions (21) (22):

[0105] in, Indicates All power generation equipment connected to the power generation node at the time of transaction Maximum power generation capacity; Indicates All load devices connected to the power consumption node at the time of transaction Maximum power consumption.

[0106] Furthermore, the electricity sales price and electricity purchase price in the virtual power plant bidding strategy should satisfy the constraints determined by the following expressions (23) (24):

[0107] in, The lowest power generation cost of all power generation equipment connected to each grid node aggregated by the virtual power plant, that is, the lowest electricity sales price; It indicates that the electricity sales price shall not be lower than the minimum power generation cost; The maximum electricity price that load users can accept, that is, the maximum electricity purchase price. If the maximum electricity price is exceeded, the user's willingness to use electricity will be reduced. It indicates that the electricity purchase price shall not be higher than the maximum electricity price.

[0108] Based on the above embodiment, as an optional embodiment, before constructing the input vector based on the predicted clearing electricity price of the grid node of the virtual power plant, it also includes: Receive valid basic information of the power generation equipment sent by the front end; the valid basic information is basic information that satisfies validity verification; the basic information is input to the front end by the user through the user interface; The valid basic information that satisfies the integrity check is stored in the database.

[0109] All distributed resources that want to participate in virtual power plant aggregation need to submit relevant equipment information, operating data and other basic information to the virtual power plant.

[0110] Figure 2 is an example diagram of submitting basic information of power generation equipment provided by the present invention, such as Figure 2 As shown, in one embodiment, the user enters basic information such as access location, rated capacity (MW), available capacity (MW), response speed, construction cost, fixed operating cost, and production cost in the user interface for information collection.

[0111] After the front end receives the basic information entered by the user through the user interface, it verifies the validity of the basic information through JavaScript, that is, verifies whether the value of the basic information entered by the user is within the set value range. If it fails the validity check, a pop-up window will be used to prompt the user to modify the input basic information. If it passes the validity check, it means that the basic information entered is valid basic information, and the valid basic information is further sent to the back-end RESTful API through AJAX calls.

[0112] After receiving the valid basic information of the power generation equipment sent by the front end, the valid basic information is checked for integrity to ensure the rationality and integrity of the data, and the valid basic information that meets the integrity check is stored in the MySQL database for further analysis and decision-making.

[0113] During the whole process, the front-end and back-end exchange data in JSON format, ensuring the efficiency and accuracy of data transmission. At the same time, the execution system of the virtual power plant power bidding strategy determination method will log all operations to track data change history and handle errors, thereby ensuring the stability of the entire system and data security.

[0114] The method for determining the power bidding strategy of a virtual power plant provided by the present invention ensures the accuracy of the data in the process of determining the power bidding strategy by performing validity verification and integrity verification on the basic information of the power generation equipment input by the user to the front end through the user interface, thereby improving the accuracy of the method for determining the power bidding strategy.

[0115] Figure 3 is an example diagram of submitting basic information of load equipment provided by the present invention, such as Figure 3As shown, in one embodiment, the user enters basic information such as access location, responsive capacity (MW), scheduling priority, response speed, peak power consumption period, etc. in the user interface of information collection. After the front end receives the basic information entered by the user through the user interface, it verifies the validity of the basic information and sends the valid basic information that passes the validity verification to the back-end RESTful API through AJAX call. After the back end receives the valid basic information, it performs integrity verification to ensure the rationality and integrity of the data.

[0116] Based on the above embodiment, as an optional embodiment, after inputting the input vector into the bidding strategy model and outputting the bidding strategy of the virtual power plant, the method further includes: Determine the magnitude relationship between the electricity selling price and the minimum electricity selling price; If the electricity selling price is lower than the minimum electricity selling price, the minimum electricity selling price is used as the new electricity selling price; the minimum electricity selling price is determined based on the minimum power generation cost of all power generation equipment in the virtual power plant; Determine the magnitude relationship between the electricity purchase price and the maximum electricity purchase price; If the electricity purchase price is higher than the maximum electricity purchase price, the maximum electricity purchase price is used as the new electricity purchase price; the maximum electricity purchase price is determined based on the electricity user's historical electricity purchase data.

[0117] Specifically, the minimum electricity selling price is determined in advance based on the lowest power generation cost of all power generation equipment connected to the grid nodes aggregated by the virtual power plant; the maximum electricity purchase price is determined in advance based on the historical electricity purchase data of electricity users. When the electricity purchase price exceeds the maximum electricity purchase price, the user's willingness to purchase electricity will be significantly reduced.

[0118] After obtaining the bidding strategy of the virtual power plant output by the bidding strategy model, the relationship between the electricity selling price and the minimum electricity selling price is judged. If the electricity selling price is lower than the minimum electricity selling price, the minimum electricity selling price will be automatically used as the new electricity selling price to ensure that there will be no loss in electricity sales.

[0119] The relationship between the electricity purchase price and the maximum electricity purchase price is also determined. If the electricity purchase price is higher than the maximum electricity purchase price, the maximum electricity purchase price is automatically used as the new electricity purchase price.

[0120] The method for determining the bidding strategy for a virtual power plant provided by the present invention, after obtaining the bidding strategy output by the bidding strategy model, automatically corrects the unreasonable electricity sales price and electricity purchase price in the bidding strategy to ensure the rationality of the bidding price, thereby ensuring that the utilization rate of the aggregated power resources can be improved, ensuring that the generated electricity can be supplied to the market, and avoiding waste of resources.

[0121] In summary, the method for determining the bidding strategy for a virtual power plant provided by the present invention performs validity verification and integrity verification and stores the data after acquiring the equipment information and operation data of distributed resources such as various power generation equipment and load equipment. By collecting and integrating the data of distributed resources, the operation status of the virtual power plant can be fully understood.

[0122] Furthermore, a machine learning-based prediction model is used to extract features from historical electricity price data, historical power generation data, historical electricity consumption data, historical weather data, equipment data and other data in the power market, so as to obtain the predicted electricity price data, predicted power generation and electricity consumption data on the trading day, providing an important basis for power bidding decisions.

[0123] Furthermore, a bidding strategy prediction model based on machine learning is used, and according to the predicted electricity price data, power generation and electricity consumption data, a bidding strategy consisting of a bidding price and a bidding capacity is obtained, so that the virtual power plant can bid to the electricity market according to the bidding strategy.

[0124] Virtual power plants participate in the day-ahead market and real-time market of the electricity market in the dual capacity of electricity sellers and buyers. When electricity prices rise, load equipment needs to purchase electricity at a higher price, resulting in more electricity expenditure, but at the same time, power generation equipment can sell electricity at a higher price and obtain more economic benefits, thereby effectively coping with the bidding risks faced by virtual power plants in the day-ahead spot market for electricity and improving the accuracy and reliability of bidding decisions. In addition to significantly improving the economic benefits and market competitiveness of virtual power plants, it can also maximize the utilization rate of aggregated power resources, ensure that the generated electricity can be supplied to the market, avoid waste of resources, and realize the intelligent and scientific bidding decision-making process of virtual power plants, with significant economic and social benefits.

[0125] Figure 4 Schematic diagram of the structure of the device for determining the bidding strategy of a virtual power plant provided by the present invention. Figure 4 As shown, the virtual power plant electricity bidding strategy determination device includes but is not limited to a vector construction module 401 and a strategy acquisition module 402.

[0126] A vector construction module 401 is used to construct an input vector based on the predicted clearing electricity price of the grid node of the virtual power plant; A strategy acquisition module 402 is used to input the input vector into a bidding strategy model and output a bidding strategy of the virtual power plant, wherein the bidding strategy includes a power selling price, a power selling capacity, a power purchasing price and a power purchasing capacity; The objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power sales revenue, power purchase expenditure and power generation cost of the virtual power plant.

[0127] It should be noted that the virtual power plant electricity bidding strategy determination device provided by the present invention can execute the virtual power plant electricity bidding strategy determination method described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0128] The present invention provides a device for determining a bidding strategy for a virtual power plant, which utilizes the producer-seller characteristics of a virtual power plant after aggregating distributed resources, and simultaneously predicts the clearing electricity price of each grid node, and then predicts a bidding strategy including electricity selling price, electricity selling capacity, electricity purchasing price and electricity purchasing capacity with the goal of maximizing total profit, so that the virtual power plant can trade in the electricity market with a dual identity, maximize the utilization rate of the aggregated electricity resources, ensure that the generated electricity can be supplied to the market, and avoid wasting resources.

[0129] Figure 5 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5 As shown, the electronic device may include: a processor (Processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 complete mutual communication through the communication bus 540. The processor 510 may call the logic instructions in the memory 530 to execute the virtual power plant power bidding strategy determination method provided by any of the above embodiments, and the virtual power plant power bidding strategy determination method includes but is not limited to the following steps: constructing an input vector based on the predicted clearing electricity price of the grid node of the virtual power plant; inputting the input vector into the bidding strategy model, and outputting the bidding strategy of the virtual power plant, the bidding strategy including the power selling price, power selling capacity, power purchasing price and power purchasing capacity; the objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power selling income, power purchasing expenditure and power generation cost of the virtual power plant.

[0130] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0131] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the virtual power plant electricity bidding strategy determination method provided in any of the above embodiments, and the virtual power plant electricity bidding strategy determination method includes but is not limited to the following steps: constructing an input vector based on the predicted clearing electricity price of the power grid node of the virtual power plant; inputting the input vector into a bidding strategy model, and outputting the bidding strategy of the virtual power plant, the bidding strategy including the electricity sales price, electricity sales capacity, electricity purchase price and electricity purchase capacity; the objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the electricity sales revenue, electricity purchase expenditure and power generation cost of the virtual power plant.

[0132] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the method for determining the power bidding strategy of a virtual power plant provided in any of the above-mentioned embodiments, the method for determining the power bidding strategy of a virtual power plant including but not limited to the following steps: constructing an input vector based on the predicted clearing electricity price of the grid node of the virtual power plant; inputting the input vector into a bidding strategy model, and outputting the bidding strategy of the virtual power plant, the bidding strategy including the power selling price, power selling capacity, power purchasing price and power purchasing capacity; the objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power selling income, power purchasing expenditure and power generation cost of the virtual power plant.

[0133] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0134] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0135] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for determining a virtual power plant power bidding strategy, characterized in that: include: Construct an input vector based on the predicted clearing electricity prices of the grid nodes of the virtual power plant; Inputting the input vector into a bidding strategy model, and outputting a bidding strategy of the virtual power plant, wherein the bidding strategy includes a power selling price, a power selling capacity, a power purchasing price, and a power purchasing capacity; The objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power sales revenue, power purchase expenditure and power generation cost of the virtual power plant.

2. The method for determining a virtual power plant power bidding strategy according to claim 1, characterized in that: The predicted clearing electricity price includes the day-ahead clearing electricity price and the real-time clearing electricity price; The predicted clearing electricity price of the grid node based on the virtual power plant is used to construct an input vector, including: The input vector is constructed using the day-ahead clearing electricity price, the real-time clearing electricity price, the predicted power generation and the predicted power consumption of the power grid node.

3. The method for determining a virtual power plant power bidding strategy according to claim 2, characterized in that: The electricity sales revenue is determined based on the day-ahead electricity sales revenue and the real-time electricity sales revenue; the electricity purchase expenditure is determined based on the day-ahead electricity purchase expenditure and the real-time electricity purchase expenditure; The day-ahead electricity sales revenue is determined based on the day-ahead clearing electricity prices and predicted power generation of all winning generation nodes; the winning generation node is a generation node whose day-ahead clearing price is greater than the electricity sales price; The real-time electricity sales revenue is determined based on the real-time clearing electricity prices and predicted power generation of all non-bid-winning power generation nodes; the non-bid-winning power generation nodes are power generation nodes whose day-ahead clearing prices are lower than the electricity sales price; The day-ahead electricity purchase expenditure is determined based on the day-ahead clearing electricity prices and predicted electricity consumption of all winning electricity consumption nodes; the winning electricity consumption node is an electricity consumption node whose day-ahead clearing electricity price is less than the electricity purchase price; The real-time electricity purchase expenditure is determined based on the real-time clearing electricity price and predicted electricity consumption of all non-bid electricity consumption nodes, and the non-bid electricity consumption nodes are electricity consumption nodes whose day-ahead clearing electricity price is greater than the electricity purchase price.

4. The method for determining a virtual power plant power bidding strategy according to claim 1, characterized in that: The power generation cost is determined based on the initial investment cost and operation and maintenance cost of all power generation equipment of the power generation node; The power generation equipment includes at least one of a photovoltaic power generation group, a wind power generation group, a pumped storage power station and an energy storage battery.

5. The method for determining a virtual power plant power bidding strategy according to claim 4, characterized in that: Before constructing the input vector based on the predicted clearing electricity price of the grid node of the virtual power plant, the following is also included: Receive valid basic information of the power generation equipment sent by the front end; the valid basic information is basic information that satisfies validity verification; the basic information is input to the front end by the user through the user interface; The valid basic information that satisfies the integrity check is stored in the database.

6. The method for determining a virtual power plant power bidding strategy according to claim 1, characterized in that: After inputting the input vector into the bidding strategy model and outputting the bidding strategy of the virtual power plant, the method further includes: Determine the magnitude relationship between the electricity selling price and the minimum electricity selling price; If the electricity selling price is lower than the minimum electricity selling price, the minimum electricity selling price is used as the new electricity selling price; the minimum electricity selling price is determined based on the minimum power generation cost of all power generation equipment in the virtual power plant; Determine the magnitude relationship between the electricity purchase price and the maximum electricity purchase price; If the electricity purchase price is higher than the maximum electricity purchase price, the maximum electricity purchase price is used as the new electricity purchase price; the maximum electricity purchase price is determined based on the electricity user's historical electricity purchase data.

7. A device for determining a virtual power plant power bidding strategy, characterized in that: include: A vector construction module, used to construct an input vector based on the predicted clearing electricity prices of the grid nodes of the virtual power plant; A strategy acquisition module, used to input the input vector into a bidding strategy model, and output a bidding strategy of the virtual power plant, wherein the bidding strategy includes a power selling price, a power selling capacity, a power purchasing price, and a power purchasing capacity; The objective function of the bidding strategy model is constructed with the goal of maximizing the total profit of the virtual power plant; the total profit is determined based on the power sales revenue, power purchase expenditure and power generation cost of the virtual power plant.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it implements the method for determining the virtual power plant electricity bidding strategy as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for determining a power bidding strategy according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, it implements the method for determining a virtual power plant electricity bidding strategy as described in any one of claims 1 to 6.

Images